Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 111 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.8853. Min Range: -0.8853

Max Act: 0.8853. Min Act: -0.0000

Data Index: 757288 (C4 (Web Text))

Max Activating Token Index: 818

Text #1

Max Range: 0.8853. Min Range: -0.8853

Max Act: 0.8689. Min Act: -0.0000

Data Index: 628359 (C4 (Web Text))

Max Activating Token Index: 37

Text #2

Max Range: 0.8853. Min Range: -0.8853

Max Act: 0.8073. Min Act: -0.0000

Data Index: 917916 (C4 (Web Text))

Max Activating Token Index: 183

Text #3

Max Range: 0.8853. Min Range: -0.8853

Max Act: 0.7426. Min Act: -0.0000

Data Index: 989321 (C4 (Web Text))

Max Activating Token Index: 323

Text #4

Max Range: 0.8853. Min Range: -0.8853

Max Act: 0.7641. Min Act: -0.0000

Data Index: 1309106 (C4 (Web Text))

Max Activating Token Index: 170

Text #5

Max Range: 0.8853. Min Range: -0.8853

Max Act: 0.7824. Min Act: -0.0000

Data Index: 1087996 (C4 (Web Text))

Max Activating Token Index: 334

Text #6

Max Range: 0.8853. Min Range: -0.8853

Max Act: 0.7546. Min Act: -0.0000

Data Index: 299042 (C4 (Web Text))

Max Activating Token Index: 58

Text #7

Max Range: 0.8853. Min Range: -0.8853

Max Act: 0.7675. Min Act: 0.0001

Data Index: 231835 (C4 (Web Text))

Max Activating Token Index: 828

Text #8

Max Range: 0.8853. Min Range: -0.8853

Max Act: 0.7240. Min Act: 0.0000

Data Index: 42233 (C4 (Web Text))

Max Activating Token Index: 731

Text #9

Max Range: 0.8853. Min Range: -0.8853

Max Act: 0.7373. Min Act: -0.0000

Data Index: 1108337 (C4 (Web Text))

Max Activating Token Index: 806

Text #10

Max Range: 0.8853. Min Range: -0.8853

Max Act: 0.7359. Min Act: -0.0000

Data Index: 474736 (C4 (Web Text))

Max Activating Token Index: 1023

Text #11

Max Range: 0.8853. Min Range: -0.8853

Max Act: 0.7895. Min Act: -0.0000

Data Index: 146471 (C4 (Web Text))

Max Activating Token Index: 228

Text #12

Max Range: 0.8853. Min Range: -0.8853

Max Act: 0.7004. Min Act: -0.0000

Data Index: 220779 (C4 (Web Text))

Max Activating Token Index: 813

Text #13

Max Range: 0.8853. Min Range: -0.8853

Max Act: 0.7138. Min Act: -0.0000

Data Index: 976510 (C4 (Web Text))

Max Activating Token Index: 893

Text #14

Max Range: 0.8853. Min Range: -0.8853

Max Act: 0.6867. Min Act: -0.0000

Data Index: 28459 (C4 (Web Text))

Max Activating Token Index: 692

Text #15

Max Range: 0.8853. Min Range: -0.8853

Max Act: 0.7022. Min Act: 0.0000

Data Index: 946812 (C4 (Web Text))

Max Activating Token Index: 20

Text #16

Max Range: 0.8853. Min Range: -0.8853

Max Act: 0.6815. Min Act: 0.0000

Data Index: 691617 (C4 (Web Text))

Max Activating Token Index: 40

Text #17

Max Range: 0.8853. Min Range: -0.8853

Max Act: 0.6633. Min Act: 0.0000

Data Index: 803595 (C4 (Web Text))

Max Activating Token Index: 637

Text #18

Max Range: 0.8853. Min Range: -0.8853

Max Act: 0.6364. Min Act: -0.0000

Data Index: 210252 (C4 (Web Text))

Max Activating Token Index: 393

Text #19

Max Range: 0.8853. Min Range: -0.8853

Max Act: 0.6294. Min Act: -0.0000

Data Index: 950838 (C4 (Web Text))

Max Activating Token Index: 39